Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Vortx-AI/emem --skill emem-device-tracesgit clone --depth 1 https://github.com/Vortx-AI/ememWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/vortx-ai/emem/emem-device-traces)<a href="https://agentmods.dev/skills/vortx-ai/emem/emem-device-traces"><img src="https://agentmods.dev/badge/skills/vortx-ai/emem/emem-device-traces/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/vortx-ai/emem/emem-device-traces"><img src="https://agentmods.dev/badge/skills/vortx-ai/emem/emem-device-traces.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.01679 |
| Opus 5.5 | $0.00000 | $0.00672 |
| Sonnet 5.5 | $0.00000 | $0.00336 |
| Haiku 4.5 | $0.00000 | $0.00168 |
Grade B, and why
emem-device-traces scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
| curl -sf -X POST https://emem.dev/v1/trace_verify -H 'content-type: application/json' -d @- \ Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sf https://emem.dev/v1/devices \ How it starts
The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
emem-device-traces
Network use. The commands in this skill send and receive JSON to
https://emem.devonly, the service the plugin's MCP server connects to. Each answer goes straight intojqto print a summary; nothing is saved, and nothing received is run. A trace is data: a JSON list of event counts and hashes, not a program.
The verify step is also an MCP tool, emem_trace_verify: call it by name with tools/call on the plugin's MCP server (tools/list on https://emem.dev/mcp/full shows it). Listing devices and resolving a trace token are REST reads only; no MCP tool covers them yet.
A device can do more than sign a reading. It can sign a trace of what
its operating system did while producing it: scheduler, memory, storage
and network activity in fixed windows, chained segment by segment and
bound to the outputs it emitted. emem stores these as
emem.os_trace.v1 records and names them emem:trace:<cid>.
What is live today is the verifier side. Hardware roots of trust (TPM, DICE, TDX, SEV-SNP, Secure Enclave, Android StrongBox and others) are registered as candidates with provisional anchors, and admit nothing yet. One device is enrolled, the operator's own software-only Linux host. Do not tell a user their robot can enrol with hardware attestation; that path ends in a rejection today.
Who is enrolled
curl -sf https://emem.dev/v1/devices \
| jq '{count, devices: [.devices[] | {device_key, platform_id, profile_id, assurance, endorsed_by, traces}]}'
Recorded on 2026-09-28: count: 1, platform generic.linux-host,
profile host.counters.v1, assurance operator_endorsed by
operator.vortx.v1, one trace.
assurance |
Means |
|---|---|
platform_attested |
a hardware anchor vouched for the device key (none admitted yet) |
operator_endorsed |
a software-only platform, vouched for by an operator anchor |
operator_asserted |
nothing was presented; enrolled by the operator directly |
Resolve and re-verify a trace
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago Changed · +9 lines · -141 tokens per session scan A → B 4858e6b66476
- 23d ago Changed · +4 lines c9eb606e11b1
- 24d ago First seen · 101 lines · 141 tokens per session scan A a4355369794f
emem-device-traces is a skill published in the GitHub repository Vortx-AI/emem (72 stars, last pushed 3d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,679 tokens. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-29.
Other skills, from other repositories
reflectworld
You have access to ReflectWorld, a visual perception and persistent memory system. It gives you eyes and memory for cameras.
reflectworld-vision-controller
VisionController dynamically adjusts camera sampling and analysis parameters based on perception results. Two policies.
reflectworld-cam
Manage video sources: add cameras, capture snapshots, start/stop monitoring, adjust settings, switch modes, watch live, list recordings.
meraki-webhooks
Receive and verify Cisco Meraki Dashboard webhook alerts. Use when setting up Meraki webhook handlers, validating the sharedSecret, or handling alert events like motionalert, settingschanged, sensoralert, or stoppedreporting.
thingctx-driver
Call a real device or service (read a sensor, send a command, fetch data) registered as a W3C WoT Thing. Use thingctx list then thingctx invoke.
smartcar-webhooks
Receive and verify Smartcar webhooks. Use when setting up Smartcar webhook handlers, debugging SC-Signature verification, responding to the VERIFY challenge, or handling vehicle events like VEHICLESTATE and VEHICLEERROR.